About
262
Publications
129,876
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,633
Citations
Publications
Publications (262)
This study provides a systematic analysis of the resource-consuming training of deep reinforcement-learning (DRL) agents for simulated low-speed automated driving (AD). In Unity, this study established two case studies: garage parking and navigating an obstacle-dense area. Our analysis involves training a path-planning agent with real-time-only sen...
Binarization is an extreme quantization technique that is attracting research in the Internet of Things (IoT) field, as it radically reduces the memory footprint of deep neural networks without a correspondingly significant accuracy drop. To support the effective deployment of Binarized Neural Networks (BNNs), we propose CBin-NN, a library of layer...
Datasets are key to developing new machine learning-based applications but are very costly to prepare, which hinders research and development in the field. We propose an edge-to-cloud end-to-end system architecture optimized for sport activity recognition dataset collection and application deployment. Tests in authentic contexts of use in four diff...
This article aims to sketch the figure of Alessandro De Gloria, a professor who dedicated his entire life, with generosity and enthusiasm, to engineering and scientific research. He designed one of the first chips in an Italian university and then a set of digital system architectures that contributed to shaping the then-fledgling field of micropro...
Recognition of driving scenarios is getting ever more relevant in research, especially for assessing performance of advanced driving assistance systems (ADAS) and automated driving functions. However, the complexity of traffic situations makes this task challenging. In order to improve the detection rate achieved through state-of-the-art deep learn...
Data analysis has become a common practice in professional and amateur sport activities, to monitor the player state and enhance performance. In tennis, performance analysis requires detecting and recognizing the different types of shots. With the advances in microcontrollers and machine learning algorithms, this topic becomes ever more considerabl...
This research explores an emerging approach, the adversarial policy learning paradigm, that aims to increase safety and robustness in deep reinforcement learning models for automated driving. We propose an iterative procedure to train an adversarial agent acting in a highway-simulated environment to attack a victim agent that is to be improved. Eac...
Research in the Internet of Things (IoT) have paved the way to a new generation of applications and services that collect huge quantities of data from the field and do a significant part of the processing on the edge. This requires availability of efficient and effective methodologies and tools for a workflow spanning from the edge to the cloud. Th...
This paper focuses on developing a Deep Reinforcement Learning (DRL)—based agent for real-time trajectory planning and tracking in a simulated parking environment, specifically low-speed maneuvers in a parking area with comb-shaped spaces and a random distribution of non-player vehicles. We rely on CARLA as a virtual driving simulator due to its re...
This paper presents a novel tool for generating driving scenario datasets, that are a key asset to advance research and development in automated driving and driver assistance systems. The tool relies on the MATLAB. Automated Driving Toolbox and focuses on the overtaking maneuver. It uses simulated vehicular data, without relying on camera-equipped...
Wearable technology has gained significant attention in research and commercial applications, including sports, where data collection and analysis play a crucial role in improving skills. This study focuses on tennis and the real-time classification of main shots, such as forehand, backhand, and serve. While previous studies have utilized machine l...
Online deep reinforcement learning training poses challenges due to its length and instability, despite the development of learning algorithms targeted to overcome these issues. Offline learning has emerged as a potential solution, but it reintroduces the issue of dataset production, which is resource-consuming and challenging even in simulation en...
Structural health monitoring is key in civil engineering because of the importance and the aging of the infrastructure. We argue that applying leading-edge, data-driven methods of large-scale complex industrial systems may be beneficial, particularly for accuracy and responsiveness. A fundamental step concerns the identification of the best tools t...
Tiny machine learning technologies are bringing intelligence ever closer to the sensor, thus enabling the key benefits of edge computing (e.g., reduced latency, improved data security, higher energy efficiency, and lower bandwidth consumption, also without the need for constant connectivity). This promises to significantly enhance industrial applic...
The relationship between decision-making and emotions has been extensively studied in both theoretical and empirical research. Game Theory-based paradigms utilizing socio-economic and trust-based contexts have been established to elicit specific emotional responses in autistic individuals. Serious games, incorporating cohesive storylines and multip...
Serious Games (SGs) are versatile tools that entertain while addressing serious issues through digital or analog gameplay. However, ensuring continuous supervision during gameplay can be challenging. To overcome this, we propose a flexible scoring system that automates procedure evaluation, empowering learners and promoting independent skill develo...
We propose a new, hierarchical architecture for behavioral planning of vehicle models usable as realistic non-player vehicles in serious games related to traffic and driving. These agents, trained with deep reinforcement learning (DRL), decide their motion by taking high-level decisions, such as “keep lane”, “overtake” and “go to rightmost lane”. T...
As timely information about a project’s state is key for management, we developed a data toolchain to support the monitoring of a project’s progress. By extending the Measurify framework, which is dedicated to efficiently building measurement-rich applications on MongoDB, we were able to make the process of setting up the reporting tool just a matt...
There is a growing body of research in the literature that investigates the relationship between emotions and decision-making in socio-economic contexts. Previous research has used Serious Games (SGs) based on game theory paradigms with socio-economic contexts to explore this relationship in controlled settings, but it is unclear whether such SGs c...
This article explores the development of a Deep Reinforcement Learning (DRL) -based agent able to perform both path planning and trajectory execution, processing sensor perception information and directly controlling the steering wheel and the acceleration, like a normal driver. As a preliminary investigation, we limit our research to low-speed man...
As the quality of perception systems available for automated driving (AD) increases, we investigate the development of an AD agent based on Reinforcement Learning which exploits underlying systems for longitudinal and lateral control. The goal is addressed by designing high-level actions, trying to imitate the commands of a real driver. The propose...
Formalization of driving scenarios is key to define the operational design domain (ODD) of Automated Driving Functions (ADF). Training machine learning (ML) requires huge datasets, that are costly to produce. We propose a toolchain to generate driving scenario video-clip datasets based on the state-of-the-art CarLA driving simulator engine. Scenari...
Measurement-oriented non-relational databases often have a fixed structure schema to better manage and guarantee integrity of their data. However, this leads to a redundancy of field values into the database or does not allow storing most of the existing measurement files. We propose a solution to massively load various format.csv datasets without...
Affective disorders can greatly influence the everyday lives of neurotypical and autistic individuals. As platforms that promote engagement, computer-based serious games (CSGs) have been previously proposed as therapies to treat affective disorders for both populations. However, these CSGs were assessed on a wide variety of experimental conditions,...
The editorial of this issue of the International Journal of Serious Games is the last one signed by our Editor in Chief and Founder, Prof. Alessandro De Gloria. Alessandro passed away in Genova, Italy, on March 20th, few days after his 68th birthday. He founded the Serious Games Society and served as its first President, then as Honorary President....
Explainability is a key requirement for users to effectively understand, trust, and manage artificial intelligence applications, especially those concerning safety. We present the design of a framework aimed at supporting a quantitative explanation of the behavioural planning performed in automated driving (AD) highway simulations by a high-level d...
As deep learning models have become increasingly complex, it is critical to understand their decision-making, particularly in safety-relevant applications. In order to support a quantitative interpretation of an autonomous agent trained through Deep Reinforcement Learning (DRL) in the highway-env simulation environment, we propose a framework featu...
The relationship between Decision-Making and emotions has been investigated in literature both through theoretical and empirical research. Particularly, some paradigms have been defined, rooted in the Game Theory, that use socio-economic and/or trust based contexts to produce specific emotional responses in people. However, experiments with such ga...
Availability of realistic driver models, also able to represent various driving styles, is key to add traffic in serious games on automotive driving. We propose a new architecture for behavioural planning of vehicles, that decide their motion taking high-level decisions, such as “keep lane”, “overtake” and “go to rightmost lane”. This is similar to...
This is a short introduction pecial issue of the International Journal of Serious Games dedicated to the selected best papers of the 2021 edition of the Games and Learning (GALA) 2021 conference. The three selected papers have undergone a regular review process. Covered topics range from cooperative games to mixed reality, from digital companions t...
The quest for efficient Tiny Machine Learning on Microcontroller Units is increasing rapidly due to the vast application spectrum made possible with the advancement of Tiny ML. One application area that could benefit from such advancement is Electronic Skin systems, that are employed in several domains such as: wearable devices, robotics, prosthesi...
Unlike conventional data such as natural images, audio and speech, raw multi-channel Electroencephalogram (EEG) data are difficult to interpret. Modern deep neural networks have shown promising results in EEG studies, however finding robust invariant representations of EEG data across subjects remains a challenge, due to differences in brain foldin...
Rail line interruptions are rare but very costly events, as they require a complete re-definition not only of the timetable of the trains, but also of their path, with major variations at least in the hit area. To the best of our knowledge, the literature is rich of documentation on timetable re-scheduling in case of delays and/or disruption of tra...
Detection of driving scenarios is getting ever more importance for assessment and control of automated driving functions. This paper investigates the performance of two versions of a high-end 3D convolutional network for scenario classification. The first one uses fully 3D kernels, the second one separates, in each constituting block, the 2D spatia...
Availability of efficient development tools for data-rich IoT applications is becoming ever more important. Such tools should support cross-platform deployment and seamless and effective applicability in a variety of domains. In this view, we assessed the versatility of an edge-to-cloud system featuring Measurify, a framework for managing smart thi...
Driving scenarios detection is an important aspect of the development of automated driving functions (ADF). Given the lack of publicly available datasets with driving scenario labels, we designed a toolchain for generating synthetic video datasets of driving scenarios, based on the OpenSCENARIO format, a well-established, public and vendor-independ...
This article investigates the feasibility of implementing a reinforcement learning agent able to plan the trajectory of a simple automated vehicle 2D model in a motorway simulation. The goal is to use it to implement a non-player vehicle in serious games for driving. The agent extends a Deep Q Learning agent developed by Eduard Leurent in Stable Ba...
The trend of bringing machine learning (ML) to the Internet of Things (IoT) field devices is becoming ever more relevant, also reducing the overall energy need of the applications. ML models are usually trained in the cloud and then deployed on edge devices. Most IoT devices generate large amounts of unlabeled data, which are expensive and challeng...
This special issue of the International Journal of Serious Games offers very valuable extensions to the best papers of the 2020 edition of the GaLA conference.
The local organization committee was composed of computer scientists of Laval (France), affiliated to Le Mans Université.
From the 9th to the 10th of December 2020, 500 participants attend...
Microcontroller Units (MCUs) are widely used for industrial field applications, and are now ever more being used also for machine learning on the edge, because of their reliability, low cost, and energy efficiency. Due to the MCU resource limitations, the deployed ML models need to be optimized particularly in terms of memory footprint. In this pap...
One of the most striking characteristics of e-Learning audiences is their diversity. Native and non-native learners can be expected among such audiences and therefore, when developing e-Learning courses it is important to consider the impact of the language level on learning. Specifically, non-native learners are expected to have a diminished audit...
Internet of Things technologies are spurring new types of instructional games, namely reality-enhanced serious games (RESGs), that support training directly in the field. This paper investigates a key feature of RESGs, i.e., user performance evaluation using real data, and studies an application of RESGs for promoting fuel-efficient driving, using...
This paper focuses on position estimation of a small unmanned aerial vehicle (UAV) using a monocular camera. Features from accelerated segment test (FAST) descriptors are used as a matched pattern to estimate differential change in position of the UAV. Visual simultaneous localization and mapping (V-SLAM) is a probabilistic filter-based method and...
Maintenance plays a fundamental role for the safety and efficiency of the railway infrastructure. This document analyzes the state of the art of technological solutions for indoor positioning, which has recently had significant developments, particularly with ultra-wide band (UWB), and can be taken into account to manage the positioning of teams of...
This paper investigated the application of unsupervised learning on a mainstream microcontroller, like the STM32 F4. We focused on the simple K-means technique, which achieved good accuracy levels on the four test datasets. These results are similar to those obtained by training a k-nearest neighbor (K-NN) classifier with the actual labels, apart f...
Statistical procedures for missing data imputation techniques have vastly improved, yet selection and suitability of optimal imputation technique for particular application\datasets\context still confusing. This works frames the missing-data problem in building energy measurement systems, review different imputation methods and suggest the optimal...
The diffusion of Internet of Things (IoT) technologies has paved the way to new applications and services. In this context, developers need tools for efficient design and implementation. This paper proposes Edgine (Edge engine), a cross-platform open-source edge computing system. The system is the edge computing extension of Measurify, a cloud Appl...
This book constitutes the refereed proceedings of the 10th International Conference on Games and Learning Alliance, GALA 2021, held in La Spezia, Italy, in December 2021.
The 21 full papers and 10 short papers were carefully reviewed and selected from 50 submissions. The papers cover a broad spectrum of topics: Serious Games Applications; Serious G...
This Editorial analyzes the manuscripts accepted, after a careful peer-reviewed process, for the Special Issue “Applications in Electronics Pervading Industry, Environment and Society—Sensing Systems and Pervasive Intelligence” of the Sensors MDPI journal [...]
This paper proposes the use of a new data toolchain for serious games analytics. The toolchain relies on the open source Measurify Internet of Things (IoT) framework, and particularly takes advantage of its edge computing extension (namely, Edgine), which can be seamlessly deployed cross-platform on embedded devices and PCs as well. The Edgine is p...
While extracting meaningful information from big data is getting relevance, literature lacks information on how to handle sensitive data by different project partners in order to collectively answer research questions (RQs), especially on impact assessment of new automated driving technologies. This paper presents the application of an established...
Auditory attention to natural speech is a complex brain process. Its quantification from physiological signals can be valuable to improving and widening the range of applications of current brain-computer-interface systems, however it remains a challenging task. In this article, we present a dataset of physiological signals collected from an experi...
As industrial research in automated driving is rapidly advancing, it is of paramount importance to analyze field data from extensive road tests. This paper investigates the design and development of a toolchain to process and manage experimental data to answer a set of research questions about the evaluation of automated driving functions at variou...
The ever more extensive data collection from IoT devices stresses the need for efficient application development tools. State of the art IoT cloud services are powerful, but the best solutions are proprietary, and there is a growing demand for interoperability and standardization. We have investigated how to develop a non vendor-locked framework, w...
This paper presents the Edge Learning Machine (ELM), a machine learning framework for edge devices, which manages the training phase on a desktop computer and performs inferences on microcontrollers. The framework implements, in a platform-independent C language, three supervised machine learning algorithms (Support Vector Machine (SVM) with a line...
As connected and, even more, autonomous vehicles are expected to bring significant novelties in the future road traffic patterns, we have investigated the control of a specific, yet very common topology, such as the intersection between two 2-lane roads. We have addressed the issue with a novel, fine-grain control approach, and proposed an adaptive...
In the Internet of Things (IoT) ecosystem, sensors and actuators represent the edge that is the source of data. The amount of data being generated by edge devices is exploding. Storage and processing of all the data in the cloud has become too slow and costly to meet the requirements of the end user. Edge computing presents a substantial solution t...
Machine learning in embedded systems has become a reality, with the first tools for neural network firmware development already being made available for ARM microcontroller developers. This paper explores the use of one of such tools, namely the STM X-Cube-AI, on mainstream ARM Cortex-M microcontrollers, analyzing their performance, and comparing s...
As dynamic inductive power transfer for electric vehicles is growing in relevance, it is important to analyze solutions towards its deployment and integration in the cloudbased services for electric mobility. In this paper we present an Internet-enabling platform for Electric Vehicle Supply Equipment, which features a high-level Charging Station Co...
This book constitutes the refereed proceedings of the 9th International Conference on Games and Learning Alliance, GALA 2020, held in Laval, France, in December 2020.
The 35 full papers and 10 short papers were carefully reviewed and selected from 77 submissions. The papers cover a broad spectrum of topics: Serious Game Design; Serious Game Analyti...
Reality-enhanced serious games (RESGs) incorporate data from the real world to enact training in the wild. This – with the proper cautions due to safety - can be done also for daily activities, such as driving. We have developed two modules that may be integrated as field user performance evaluators in third-party RESGs, aimed at improving driver’s...
Pervasive games are an emerging genre combining reality and computing. This paper presents a suite of simple pervasive serious games we have developed to explore the concept of “reality-enhanced gaming”, a pattern to tie game play mechanics to the outcomes/measurements of real-world activities. The prototype games were realized in the context of TE...
Analyzing road-test data is important for developing automated vehicles. L3Pilot is a European pilot project on level 3 automation, including 34 partners among manufacturers, suppliers and research institutions. Targeting around 100 cars and 1000 test subjects, the project will generate large amounts of data. We present a data format, allowing effi...
There is a trend in industries towards adoption of new technologies coming from Industry 4.0 to improve operational automation, efficiency, maintenance, by interconnecting sensors, devices, machines, and processes, increasing data availability for automation and decision support. These changing scenarios need to be addressed also in terms of instru...
With the appearance of tools to support the emerging paradigm of edge computing, we expect that low cost microcontrollers will become appealing execution platforms also for machine learning. To explore this field, we implemented Machine Learning eMbedded Library (ML)² and tested it in a simple case (classifying human movement as normal or not) and...
Artificial vision is a key factor for new generation automotive systems. This paper focuses on a module aimed at maximizing the energy flow between the transmitting and receiving grids, in the context of dynamic wireless charging of electrical vehicles. The output of the module helps the driver to keep a precise alignment between the vehicle and th...
Electric vehicle (EV) limited range is a serious concern for its wide scale commercialization. Dynamic battery charging is being developed as a promising technology for increasing the range, vehicles are charged through inductive points placed in the net. The choice of a proper navigation route becomes essential, and algorithms must be identified f...